Search

Your search keyword '"Gu, Jian"' showing total 5,099 results
Start Over Author "Gu, Jian"
5,099 results on '"Gu, Jian"'

59. Interpretable Foreground Object Search As Knowledge Distillation

Author

Li, Boren, Zhuang, Po-Yu, Gu, Jian, Li, Mingyang, and Tan, Ping

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

This paper proposes a knowledge distillation method for foreground object search (FoS). Given a background and a rectangle specifying the foreground location and scale, FoS retrieves compatible foregrounds in a certain category for later image composition. Foregrounds within the same category can be grouped into a small number of patterns. Instances within each pattern are compatible with any query input interchangeably. These instances are referred to as interchangeable foregrounds. We first present a pipeline to build pattern-level FoS dataset containing labels of interchangeable foregrounds. We then establish a benchmark dataset for further training and testing following the pipeline. As for the proposed method, we first train a foreground encoder to learn representations of interchangeable foregrounds. We then train a query encoder to learn query-foreground compatibility following a knowledge distillation framework. It aims to transfer knowledge from interchangeable foregrounds to supervise representation learning of compatibility. The query feature representation is projected to the same latent space as interchangeable foregrounds, enabling very efficient and interpretable instance-level search. Furthermore, pattern-level search is feasible to retrieve more controllable, reasonable and diverse foregrounds. The proposed method outperforms the previous state-of-the-art by 10.42% in absolute difference and 24.06% in relative improvement evaluated by mean average precision (mAP). Extensive experimental results also demonstrate its efficacy from various aspects. The benchmark dataset and code will be release shortly., Comment: This paper will appear at ECCV 2020

Published
2020

60. Superoptimization of WebAssembly Bytecode

Author

Cabrera-Arteaga, Javier, Donde, Shrinish, Gu, Jian, Floros, Orestis, Satabin, Lucas, Baudry, Benoit, and Monperrus, Martin

Subjects
Computer Science - Programming Languages, Computer Science - Software Engineering
Abstract

Motivated by the fast adoption of WebAssembly, we propose the first functional pipeline to support the superoptimization of WebAssembly bytecode. Our pipeline works over LLVM and Souper. We evaluate our superoptimization pipeline with 12 programs from the Rosetta code project. Our pipeline improves the code section size of 8 out of 12 programs. We discuss the challenges faced in superoptimization of WebAssembly with two case studies., Comment: 4 pages, 3 figures. Proceedings of MoreVMs: Workshop on Modern Language Runtimes, Ecosystems, and VMs (2020)

Published
2020
Full Text
View/download PDF

61. LE-HGR: A Lightweight and Efficient RGB-based Online Gesture Recognition Network for Embedded AR Devices

Author

Xie, Hongwei, Wang, Jiafang, Shao, Baitao, Gu, Jian, and Li, Mingyang

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Online hand gesture recognition (HGR) techniques are essential in augmented reality (AR) applications for enabling natural human-to-computer interaction and communication. In recent years, the consumer market for low-cost AR devices has been rapidly growing, while the technology maturity in this domain is still limited. Those devices are typical of low prices, limited memory, and resource-constrained computational units, which makes online HGR a challenging problem. To tackle this problem, we propose a lightweight and computationally efficient HGR framework, namely LE-HGR, to enable real-time gesture recognition on embedded devices with low computing power. We also show that the proposed method is of high accuracy and robustness, which is able to reach high-end performance in a variety of complicated interaction environments. To achieve our goal, we first propose a cascaded multi-task convolutional neural network (CNN) to simultaneously predict probabilities of hand detection and regress hand keypoint locations online. We show that, with the proposed cascaded architecture design, false-positive estimates can be largely eliminated. Additionally, an associated mapping approach is introduced to track the hand trace via the predicted locations, which addresses the interference of multi-handedness. Subsequently, we propose a trace sequence neural network (TraceSeqNN) to recognize the hand gesture by exploiting the motion features of the tracked trace. Finally, we provide a variety of experimental results to show that the proposed framework is able to achieve state-of-the-art accuracy with significantly reduced computational cost, which are the key properties for enabling real-time applications in low-cost commercial devices such as mobile devices and AR/VR headsets., Comment: Published in: 2019 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)

Published
2020
Full Text
View/download PDF

62. Distinct germline genetic susceptibility profiles identified for common non-Hodgkin lymphoma subtypes

Author

Berndt, Sonja I., Vijai, Joseph, Benavente, Yolanda, Camp, Nicola J., Nieters, Alexandra, Wang, Zhaoming, Smedby, Karin E., Kleinstern, Geffen, Hjalgrim, Henrik, Besson, Caroline, Skibola, Christine F., Morton, Lindsay M., Brooks-Wilson, Angela R., Teras, Lauren R., Breeze, Charles, Arias, Joshua, Adami, Hans-Olov, Albanes, Demetrius, Anderson, Kenneth C., Ansell, Stephen M., Bassig, Bryan, Becker, Nikolaus, Bhatti, Parveen, Birmann, Brenda M., Boffetta, Paolo, Bracci, Paige M., Brennan, Paul, Brown, Elizabeth E., Burdett, Laurie, Cannon-Albright, Lisa A., Chang, Ellen T., Chiu, Brian C. H., Chung, Charles C., Clavel, Jacqueline, Cocco, Pierluigi, Colditz, Graham, Conde, Lucia, Conti, David V., Cox, David G., Curtin, Karen, Casabonne, Delphine, De Vivo, Immaculata, Diepstra, Arjan, Diver, W. Ryan, Dogan, Ahmet, Edlund, Christopher K., Foretova, Lenka, Fraumeni, Jr, Joseph F., Gabbas, Attilio, Ghesquières, Hervé, Giles, Graham G., Glaser, Sally, Glenn, Martha, Glimelius, Bengt, Gu, Jian, Habermann, Thomas M., Haiman, Christopher A., Haioun, Corinne, Hofmann, Jonathan N., Holford, Theodore R., Holly, Elizabeth A., Hutchinson, Amy, Izhar, Aalin, Jackson, Rebecca D., Jarrett, Ruth F., Kaaks, Rudolph, Kane, Eleanor, Kolonel, Laurence N., Kong, Yinfei, Kraft, Peter, Kricker, Anne, Lake, Annette, Lan, Qing, Lawrence, Charles, Li, Dalin, Liebow, Mark, Link, Brian K., Magnani, Corrado, Maynadie, Marc, McKay, James, Melbye, Mads, Miligi, Lucia, Milne, Roger L., Molina, Thierry J., Monnereau, Alain, Montalvan, Rebecca, North, Kari E., Novak, Anne J., Onel, Kenan, Purdue, Mark P., Rand, Kristin A., Riboli, Elio, Riby, Jacques, Roman, Eve, Salles, Gilles, Sborov, Douglas W., Severson, Richard K., Shanafelt, Tait D., Smith, Martyn T., Smith, Alexandra, Song, Kevin W., Song, Lei, Southey, Melissa C., Spinelli, John J., Staines, Anthony, Stephens, Deborah, Sutherland, Heather J., Tkachuk, Kaitlyn, Thompson, Carrie A., Tilly, Hervé, Tinker, Lesley F., Travis, Ruth C., Turner, Jenny, Vachon, Celine M., Vajdic, Claire M., Van Den Berg, Anke, Van Den Berg, David J., Vermeulen, Roel C. H., Vineis, Paolo, Wang, Sophia S., Weiderpass, Elisabete, Weiner, George J., Weinstein, Stephanie, Doo, Nicole Wong, Ye, Yuanqing, Yeager, Meredith, Yu, Kai, Zeleniuch-Jacquotte, Anne, Zhang, Yawei, Zheng, Tongzhang, Ziv, Elad, Sampson, Joshua, Chatterjee, Nilanjan, Offit, Kenneth, Cozen, Wendy, Wu, Xifeng, Cerhan, James R., Chanock, Stephen J., Slager, Susan L., and Rothman, Nathaniel

Published
2022
Full Text
View/download PDF

65. Automated Classification of Overfitting Patches with Statically Extracted Code Features

Author

Ye, He, Gu, Jian, Martinez, Matias, Durieux, Thomas, and Monperrus, Martin

Subjects
Computer Science - Software Engineering
Abstract

Automatic program repair (APR) aims to reduce the cost of manually fixing software defects. However, APR suffers from generating a multitude of overfitting patches, those patches that fail to correctly repair the defect beyond making the tests pass. This paper presents a novel overfitting patch detection system called ODS to assess the correctness of APR patches. ODS first statically compares a patched program and a buggy program in order to extract code features at the abstract syntax tree (AST) level. Then, ODS uses supervised learning with the captured code features and patch correctness labels to automatically learn a probabilistic model. The learned ODS model can then finally be applied to classify new and unseen program repair patches. We conduct a large-scale experiment to evaluate the effectiveness of ODS on patch correctness classification based on 10,302 patches from Defects4J, Bugs.jar and Bears benchmarks. The empirical evaluation shows that ODS is able to correctly classify 71.9% of program repair patches from 26 projects, which improves the state-of-the-art. ODS is applicable in practice and can be employed as a post-processing procedure to classify the patches generated by different APR systems.

Published
2019
Full Text
View/download PDF

66. Seq-SG2SL: Inferring Semantic Layout from Scene Graph Through Sequence to Sequence Learning

Author

Li, Boren, Zhuang, Boyu, Li, Mingyang, and Gu, Jian

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Generating semantic layout from scene graph is a crucial intermediate task connecting text to image. We present a conceptually simple, flexible and general framework using sequence to sequence (seq-to-seq) learning for this task. The framework, called Seq-SG2SL, derives sequence proxies for the two modality and a Transformer-based seq-to-seq model learns to transduce one into the other. A scene graph is decomposed into a sequence of semantic fragments (SF), one for each relationship. A semantic layout is represented as the consequence from a series of brick-action code segments (BACS), dictating the position and scale of each object bounding box in the layout. Viewing the two building blocks, SF and BACS, as corresponding terms in two different vocabularies, a seq-to-seq model is fittingly used to translate. A new metric, semantic layout evaluation understudy (SLEU), is devised to evaluate the task of semantic layout prediction inspired by BLEU. SLEU defines relationships within a layout as unigrams and looks at the spatial distribution for n-grams. Unlike the binary precision of BLEU, SLEU allows for some tolerances spatially through thresholding the Jaccard Index and is consequently more adapted to the task. Experimental results on the challenging Visual Genome dataset show improvement over a non-sequential approach based on graph convolution., Comment: This paper will appear at ICCV 2019

Published
2019

69. Using genome and transcriptome data from African-ancestry female participants to identify putative breast cancer susceptibility genes

Author

Ping, Jie, Jia, Guochong, Cai, Qiuyin, Guo, Xingyi, Tao, Ran, Ambrosone, Christine, Huo, Dezheng, Ambs, Stefan, Barnard, Mollie E., Chen, Yu, Garcia-Closas, Montserrat, Gu, Jian, Hu, Jennifer J., John, Esther M., Li, Christopher I., Nathanson, Katherine, Nemesure, Barbara, Olopade, Olufunmilayo I., Pal, Tuya, Press, Michael F., Sanderson, Maureen, Sandler, Dale P., Yoshimatsu, Toshio, Adejumo, Prisca O., Ahearn, Thomas, Brewster, Abenaa M., Hennis, Anselm J. M., Makumbi, Timothy, Ndom, Paul, O’Brien, Katie M., Olshan, Andrew F., Oluwasanu, Mojisola M., Reid, Sonya, Yao, Song, Butler, Ebonee N., Huang, Maosheng, Ntekim, Atara, Li, Bingshan, Troester, Melissa A., Palmer, Julie R., Haiman, Christopher A., Long, Jirong, and Zheng, Wei

Published
2024
Full Text
View/download PDF

76. Case-Case Genome-Wide Analyses Identify Subtype-Informative Variants that Confer Risk for Breast Cancer

Author

Sun, Xiaohui, primary, Verma, Shiv Prakash, additional, Jia, Guochong, additional, Wang, Xinjun, additional, Ping, Jie, additional, Guo, Xingyi, additional, Shu, Xiao-Ou, additional, Chen, Jianhong, additional, Derkach, Andriy, additional, Cai, Qiuyin, additional, Liang, Xiaolin, additional, Long, Jirong, additional, Offit, Kenneth, additional, Oh, Jung Hun, additional, Reiner, Anne S., additional, Watt, Gordon P., additional, Woods, Meghan, additional, Yang, Yaohua, additional, Ambrosone, Christine B., additional, Ambs, Stefan, additional, Chen, Yu, additional, Concannon, Patrick, additional, Garcia-Closas, Montserrat, additional, Gu, Jian, additional, Haiman, Christopher A., additional, Hu, Jennifer J., additional, Huo, Dezheng, additional, John, Esther M., additional, Knight, Julia A., additional, Li, Christopher I., additional, Lynch, Charles F., additional, Mellemkjaer, Lene, additional, Nathanson, Katherine L., additional, Nemesure, Barbara, additional, Olopade, Olufunmilayo I., additional, Olshan, Andrew F., additional, Pal, Tuya, additional, Palmer, Julie R., additional, Press, Michael F., additional, Sanderson, Maureen, additional, Sandler, Dale P., additional, Troester, Melissa A., additional, Zheng, Wei, additional, Bernstein, Jonine L., additional, Buas, Matthew F., additional, and Shu, Xiang, additional

Published
2024
Full Text
View/download PDF

82. Correction: Distinct germline genetic susceptibility profiles identified for common non-Hodgkin lymphoma subtypes

Author

Berndt, Sonja I., Vijai, Joseph, Benavente, Yolanda, Camp, Nicola J., Nieters, Alexandra, Wang, Zhaoming, Smedby, Karin E., Kleinstern, Geffen, Hjalgrim, Henrik, Besson, Caroline, Skibola, Christine F., Morton, Lindsay M., Brooks-Wilson, Angela R., Teras, Lauren R., Breeze, Charles, Arias, Joshua, Adami, Hans-Olov, Albanes, Demetrius, Anderson, Kenneth C., Ansell, Stephen M., Bassig, Bryan, Becker, Nikolaus, Bhatti, Parveen, Birmann, Brenda M., Boffetta, Paolo, Bracci, Paige M., Brennan, Paul, Brown, Elizabeth E., Burdett, Laurie, Cannon-Albright, Lisa A., Chang, Ellen T., Chiu, Brian C. H., Chung, Charles C., Clavel, Jacqueline, Cocco, Pierluigi, Colditz, Graham, Conde, Lucia, Conti, David V., Cox, David G., Curtin, Karen, Casabonne, Delphine, De Vivo, Immaculata, Diepstra, Arjan, Diver, W. Ryan, Dogan, Ahmet, Edlund, Christopher K., Foretova, Lenka, Fraumeni, Jr, Joseph F., Gabbas, Attilio, Ghesquières, Hervé, Giles, Graham G., Glaser, Sally, Glenn, Martha, Glimelius, Bengt, Gu, Jian, Habermann, Thomas M., Haiman, Christopher A., Haioun, Corinne, Hofmann, Jonathan N., Holford, Theodore R., Holly, Elizabeth A., Hutchinson, Amy, Izhar, Aalin, Jackson, Rebecca D., Jarrett, Ruth F., Kaaks, Rudolph, Kane, Eleanor, Kolonel, Laurence N., Kong, Yinfei, Kraft, Peter, Kricker, Anne, Lake, Annette, Lan, Qing, Lawrence, Charles, Li, Dalin, Liebow, Mark, Link, Brian K., Magnani, Corrado, Maynadie, Marc, McKay, James, Melbye, Mads, Miligi, Lucia, Milne, Roger L., Molina, Thierry J., Monnereau, Alain, Montalvan, Rebecca, North, Kari E., Novak, Anne J., Onel, Kenan, Purdue, Mark P., Rand, Kristin A., Riboli, Elio, Riby, Jacques, Roman, Eve, Salles, Gilles, Sborov, Douglas W., Severson, Richard K., Shanafelt, Tait D., Smith, Martyn T., Smith, Alexandra, Song, Kevin W., Song, Lei, Southey, Melissa C., Spinelli, John J., Staines, Anthony, Stephens, Deborah, Sutherland, Heather J., Tkachuk, Kaitlyn, Thompson, Carrie A., Tilly, Hervé, Tinker, Lesley F., Travis, Ruth C., Turner, Jenny, Vachon, Celine M., Vajdic, Claire M., Van Den Berg, Anke, Van Den Berg, David J., Vermeulen, Roel C. H., Vineis, Paolo, Wang, Sophia S., Weiderpass, Elisabete, Weiner, George J., Weinstein, Stephanie, Doo, Nicole Wong, Ye, Yuanqing, Yeager, Meredith, Yu, Kai, Zeleniuch-Jacquotte, Anne, Zhang, Yawei, Zheng, Tongzhang, Ziv, Elad, Sampson, Joshua, Chatterjee, Nilanjan, Offit, Kenneth, Cozen, Wendy, Wu, Xifeng, Cerhan, James R., Chanock, Stephen J., Slager, Susan L., and Rothman, Nathaniel

Published
2023
Full Text
View/download PDF

88. Pain

Author

Chen, Jun, Han, Ji-Sheng, Zhao, Zhi-Qi, Wei, Feng, Hsieh, Jen-Chuen, Bao, Lan, Chen, Andrew C. N., Dai, Yi, Fan, Bi-Fa, Gu, Jian-Guo, Hao, Shuang-Lin, Hu, San-Jue, Ji, Yong-Hua, Li, Yong-Jie, Li, Yun-Qing, Lin, Qing, Liu, Xian-Guo, Liu, Yan-Qing, Lu, Yan, Luo, Fei, Ma, Chao, Qiu, Yun-Hai, Rao, Zhi-Ren, Shi, Lin, Shyu, Bai-Chuang, Song, Xue-Jun, Tang, Jing-Shi, Tao, Yuan-Xiang, Wan, You, Wang, Jia-Shuang, Wang, Ke-Wei, Wang, Yun, Xu, Guang-Yin, Xu, Tian-Le, You, Hao-Jun, Yu, Long-Chuan, Yu, Sheng-Yuan, Zhang, Da-Ying, Zhang, De-Ren, Zhang, Jun-Ming, Zhang, Xu, Zhang, Yu-Qiu, Zhuo, Min, Pfaff, Donald W., editor, Volkow, Nora D., editor, and Rubenstein, John L., editor

Published
2022
Full Text
View/download PDF

89. Disturbance Observer Compensation Based on Sliding-Mode Approach for Solving Compliant Actuator Tracking Control Problems

Author

Xu, Changxian, Gu, Jian, Liu, Yongbai, Zhao, Liming, Sun, Zhongbo, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Liu, Honghai, editor, Yin, Zhouping, editor, Liu, Lianqing, editor, Jiang, Li, editor, Gu, Guoying, editor, Wu, Xinyu, editor, and Ren, Weihong, editor

Published
2022
Full Text
View/download PDF

90. Impedance Control of Upper Limb Rehabilitation Robot Based on Series Elastic Actuator

Author

Gu, Jian, Xu, Changxian, Liu, Keping, Zhao, Liming, He, Tianyu, Sun, Zhongbo, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Liu, Honghai, editor, Yin, Zhouping, editor, Liu, Lianqing, editor, Jiang, Li, editor, Gu, Guoying, editor, Wu, Xinyu, editor, and Ren, Weihong, editor

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results